搜索结果：fight

Humanoid robots have demonstrated impressive motor skills in a wide range of tasks, yet whole-body control for humanlike long-time, dynamic fighting remains particularly challenging due to the stringent requirements on agility and stability. While imitation learning enables robots to execute human-like fighting skills, existing approaches often rely on switching among multiple single-skill policies or employing a general policy to imitate input reference motions. These strategies suffer from instability when transitioning between skills, as the mismatch of initial and terminal states across skills or reference motions introduces out-of-domain disturbances, resulting in unsmooth or unstable behaviors. In this work, we propose RPG, a hybrid expert policy framework, for smooth and stable humanoid multi-skills transition. Our approach incorporates motion transition randomization and temporal randomization to train a unified policy that generates agile fighting actions with stability and smoothness during skill transitions. Furthermore, we design a control pipeline that integrates walking/running locomotion with fighting skills, allowing humanlike long-time combat of arbitrary duration

The Ultimate Fighting Championship (UFC) has grown from a niche combat sport promotion into a globally recognized competitive enterprise. This study applies complex network analysis to explore the structural evolution of UFC matchmaking and its impact on competitive dynamics, fighter prominence, and audience engagement. By constructing directed and undirected networks where fighters represent nodes and bouts define edges, we examine key metrics such as degree distribution, clustering, betweenness centrality, and eigenvector centrality. Our findings reveal how the UFC's matchmaking strategies transitioned from tightly clustered, repetitive matchups in its early years to a more decentralized and strategically curated fight network. We identify distinct structural properties between winners and losers, showing that successful fighters maintain centrality while frequently losing fighters exhibit surprising degrees of sustained connectivity. Correlations with Pay-Per-View sales and Google search trends suggest that network dispersion and novelty in matchups drive greater audience interest, while excessive clustering and density reduce engagement. Furthermore, comparisons with official r

We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis. We provide a vectorized simulator that enables high-throughput training on standard hardware, making the environment accessible and reproducible. We describe the design of the environment, benchmark several reinforcement learning algorithms, and discuss open research directions it enables. The code is available at https://github.com/como-research/FootsiesGym.

Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce LM Fight Arena (Large Model Fight Arena), a novel framework that evaluates LMMs by pitting them against each other in the classic fighting game Mortal Kombat II, a task requiring rapid visual understanding and tactical, sequential decision-making. In a controlled tournament, we test six leading open- and closed-source models, where each agent operates controlling the same character to ensure a fair comparison. The models are prompted to interpret game frames and state data to select their next actions. Unlike static evaluations, LM Fight Arena provides a fully automated, reproducible, and objective assessment of an LMM's strategic reasoning capabilities in a dynamic setting. This work introduces a challenging and engaging benchmark that bridges the gap between AI evaluation and interactive entertainment.

Deceptive patterns, dark patterns, and manipulative user interfaces (UI) are a widely used design strategy that manipulates users to act against their own interests in pursuit of shareholder aims. These patterns may particularly affect people with less education, visual impairments, and older adults. Yet, access is a critical feature of the user experience (UX), development standards, and law. We considered whether and how the Web Content Accessibility Guidelines (WCAG) and related legislation, like the European Accessibility Act (EAA), could act as a tool against deceptive patterns. We used heuristic evaluation to analyze whether and how deceptive patterns violate or conform to these guidelines and legal statutes. Although statistical analysis revealed no significant differences by pattern type, we identified three patterns implicated by the WCAG guidelines: Countdown Timer, Auto-Play, and Hidden Information. We offer this approach as one tool in the fight against UI-based deception and in support of inclusive design.

This paper presents a new competition -- at the 2022 IEEE Conference on Games (CoG) -- called DareFightingICE Competition. The competition has two tracks: a sound design track and an AI track. The game platform for this competition is also called DareFightingICE, a fighting game platform. DareFightingICE is a sound-design-enhanced version of FightingICE, used earlier in a competition at CoG until 2021 to promote artificial intelligence (AI) research in fighting games. In the sound design track, participants compete for the best sound design, given the default sound design of DareFightingICE as a sample, where we define a sound design as a set of sound effects combined with the source code that implements their timing-control algorithm. Participants of the AI track are asked to develop their AI algorithm that controls a character given only sound as the input (blind AI) to fight against their opponent; a sample deep-learning blind AI will be provided by us. Our means to maximize the synergy between the two tracks are also described. This competition serves to come up with effective sound designs for visually impaired players, a group in the gaming community which has been mostly ign

Detecting fights from still images shared on social media is an important task required to limit the distribution of violent scenes in order to prevent their negative effects. For this reason, in this study, we address the problem of fight detection from still images collected from the web and social media. We explore how well one can detect fights from just a single still image. We also propose a new dataset, named Social Media Fight Images (SMFI), comprising real-world images of fight actions. Results of the extensive experiments on the proposed dataset show that fight actions can be recognized successfully from still images. That is, even without exploiting the temporal information, it is possible to detect fights with high accuracy by utilizing appearance only. We also perform cross-dataset experiments to evaluate the representation capacity of the collected dataset. These experiments indicate that, as in the other computer vision problems, there exists a dataset bias for the fight recognition problem. Although the methods achieve close to 100% accuracy when trained and tested on the same fight dataset, the cross-dataset accuracies are significantly lower, i.e., around 70% when

"Train While You Fight" (TWYF) advocates for continuous learning that occurs during operations, not just before or after. This paper examines the technical requirements that advanced distributed learning (ADL) platforms must meet to support TWYF, and how existing software engineering patterns can fulfill these requirements. Using a Design Science Research approach, we (i) derive challenges from PfPC/NATO documentation and recent practice, (ii) define solution objectives, and (iii) conduct a systematic mapping from challenges to proven patterns. We identify seven technical challenges: interoperability, resilience, multilingual support, data security and privacy, scalability, platform independence, and modularity. We illustrate the patterns with a national use case from the German armed forces.

We introduce extended fighting fish as branching surfaces that can also be seen as walks in the quarter plane defined by simple rewriting rules. The main result we present in the article is a direct bijection between extended fighting fish and intervals of the Tamari lattice that exchanges multiple natural statistics. The model includes the recently introduced fighting fish of (Duchi, Guerrini, Rinaldi, Schaeffer 2017) that were shown to be equinumerated with synchronized Tamari intervals. Using the dual surface/walk points of view on extended fighting fish, we show that the area statistics on these fish corresponds to the distance statistics (or maximal length of a chain) in Tamari invervals. We also show that the average area of a uniform random extended fighting fish of size $n$, and hence the average distance over the set of Tamari intervals of size $n$, is of order $n^{5/4}$, in accordance with earlier result for the subclass fighting fish.

In this paper of a research based project, using Bidirectional Long Short-Term Memory (BiLSTM) networks, we provide a novel Fight Scene Detection (FSD) model which can be used for Movie Highlight Generation Systems (MHGS) based on deep learning and Neural Networks . Movies usually have Fight Scenes to keep the audience amazed. For trailer generation, or any other application of Highlight generation, it is very tidious to first identify all such scenes manually and then compile them to generate a highlight serving the purpose. Our proposed FSD system utilises temporal characteristics of the movie scenes and thus is capable to automatically identify fight scenes. Thereby helping in the effective production of captivating movie highlights. We observe that the proposed solution features 93.5% accuracy and is higher than 2D CNN with Hough Forests which being 92% accurate and is significantly higher than 3D CNN which features an accuracy of 65%.

This study investigates who should bear the responsibility of combating the spread of misinformation in social networks. Should that be the online platforms or their users? Should that be done by debunking the "fake news" already in circulation or by investing in preemptive efforts to prevent their diffusion altogether? We seek to answer such questions in a stylized opinion dynamics framework, where agents in a network aggregate the information they receive from peers and/or from influential external sources, with the aim of learning a ground truth among a set of competing hypotheses. In most cases, we find centralized sources to be more effective at combating misinformation than distributed ones, suggesting that online platforms should play an active role in the fight against fake news. In line with literature on the "backfire effect", we find that debunking in certain circumstances can be a counterproductive strategy, whereas some targeted strategies (akin to "deplatforming") and/or preemptive campaigns turn out to be quite effective. Despite its simplicity, our model provides useful guidelines that could inform the ongoing debate on online disinformation and the best ways to lim

This study examined the impact of social media in the fight against the spread of coronavirus (COVID-19) pandemic in Anambra state, Nigeria. The key objectives are to: find out if the numbers of social media users increased in Anambra state since the wake of coronavirus pandemic; find out if the social media is being utilised in the fight against the spread of coronavirus pandemic in Anambra state; find out how the social media is being utilised in the fight against the spread of coronavirus pandemic in Anambra state; and discover the impact of social media in the fight against the spread of coronavirus pandemic in Anambra State. It was anchored on Agenda Setting Theory, and the Technological Determinism Theory (TDT). The study was designed as a survey with close-ended questionnaire distributed to 400 respondents. The findings of this study revealed that usage and accessibility of social media increased in Anambra state because of coronavirus pandemic. It also revealed that the social media is being utilised by individuals, NGOs and government in the fight against the spread of coronavirus in Anambra state. The study also found that the social media is being utilised to gather and

Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player interaction. In this paper, we propose a practical DRL agent system for fighting games named Shūkai, which has been successfully deployed to Naruto Mobile, a popular fighting game with over 100 million registered users. Shūkai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency. Furthermore, Shūkai implements specific rewards to align the agent's behavior with human expectations. Shūkai's ability to generalize is demonstrated by its consistent competence across all characters, even though it was trained on only 13% of them. Additionally, HELT exhibits a remarkable 22% improvement in sample efficiency. Shūkai serves as a valuable training partner for players in Naruto Mobile, enabling them to enhance their abilities and skills.

Detection of fights is an important surveillance application in videos. Most existing methods use supervised binary action recognition. Since frame-level annotations are very hard to get for anomaly detection, weakly supervised learning using multiple instance learning is widely used. This paper explores the detection of fights in videos as one special type of anomaly detection and as binary action recognition. We use the UBI-Fight and NTU-CCTV-Fight datasets for most of the study since they have frame-level annotations. We find that the anomaly detection has similar or even better performance than the action recognition. Furthermore, we study to use anomaly detection as a toolbox to generate training datasets for action recognition in an iterative way conditioned on the performance of the anomaly detection. Experiment results should show that we achieve state-of-the-art performance on three fight detection datasets.

The class of fighting fish is a recently introduced model of branching surfaces generalizing parallelogram polyominoes. We can alternatively see them as gluings of cells, walks on the square lattice confined to the quadrant or shuffle of Dyck words. With these different points of view, we introduce a natural extension of fighting fish that we call \emph{generalized fighting fish}. We show that generalized fighting fish are exactly the Mullin codes of rooted planar maps endowed with their unique rightmost depth-first search spanning tree, also known as Lehman-Lenormand code. In particular, this correspondence gives a bijection between fighting fish and nonseparable rooted planar maps, enriching the garden of bijections between classes of objects enumerated by the sequence $\frac{2}{(n+1)(2n+1)} \binom{3n}{n}$.

The advent of deep learning (DL) gave rise to significant breakthroughs in Reinforcement Learning (RL) research. Deep Reinforcement Learning (DRL) algorithms have reached super-human level skills when applied to vision-based control problems as such in Atari 2600 games where environment states were extracted from pixel information. Unfortunately, these environments are far from being applicable to highly dynamic and complex real-world tasks as in autonomous control of a fighter aircraft since these environments only involve 2D representation of a visual world. Here, we present a semi-realistic flight simulation environment Harfang3D Dog-Fight Sandbox for fighter aircrafts. It is aimed to be a flexible toolbox for the investigation of main challenges in aviation studies using Reinforcement Learning. The program provides easy access to flight dynamics model, environment states, and aerodynamics of the plane enabling user to customize any specific task in order to build intelligent decision making (control) systems via RL. The software also allows deployment of bot aircrafts and development of multi-agent tasks. This way, multiple groups of aircrafts can be configured to be competitiv

The quality of opponent Artificial Intelligence (AI) in fighting videogames is crucial. Some other game genres can rely on their story or visuals, but fighting games are all about the adversarial experience. In this paper, we will introduce standard behavior algorithms in videogames, such as Finite-State Machines and Behavior Trees, as well as more recent developments, such as Monte-Carlo Tree Search. We will also discuss the existing and potential combinations of these algorithms, and how they might be used in fighting games. Since we are at the financial peak of fighting games, both for casual players and in tournaments, it is important to build and expand on fighting game AI, as it is one of the pillars of this growing market.

Fight detection in videos is an emerging deep learning application with today's prevalence of surveillance systems and streaming media. Previous work has largely relied on action recognition techniques to tackle this problem. In this paper, we propose a simple but effective method that solves the task from a new perspective: we design the fight detection model as a composition of an action-aware feature extractor and an anomaly score generator. Also, considering that collecting frame-level labels for videos is too laborious, we design a weakly supervised two-stage training scheme, where we utilize multiple-instance-learning loss calculated on video-level labels to train the score generator, and adopt the self-training technique to further improve its performance. Extensive experiments on a publicly available large-scale dataset, UBI-Fights, demonstrate the effectiveness of our method, and the performance on the dataset exceeds several previous state-of-the-art approaches. Furthermore, we collect a new dataset, VFD-2000, that specializes in video fight detection, with a larger scale and more scenarios than existing datasets. The implementation of our method and the proposed dataset

Fighting fish were very recently introduced by the authors as combinatorial structures made of square tiles that form two dimensional branching surfaces. A main feature of these fighting fish is that the area of uniform random fish of size $n$ scales like $n^{5/4}$ as opposed to the typical $n^{3/2}$ area behavior of the staircase or direct convex polyominoes that they generalize. In this extended abstract we concentrate on enumerative properties of fighting fish: in particular we provide a new decomposition and we show that the number of fighting fish with $i$ left lower free edges and $j$ right lower free edges is equal to \begin{equation*} \frac{(2i+j-2)!(2j+i-2)!}{i!j!(2i-1)!(2j-1)!}. \end{equation*} These numbers are known to count rooted planar non-separable maps with $i+1$ vertices and $j+1$ faces, or two-stack-sortable permutations with respect to ascending and descending runs, or left ternary trees with respect to vertices with even and odd abscissa. However we have been unable until now to provide any explicit bijection between our fish and such structures. Instead we provide new refined generating series for left ternary trees to prove further equidistribution results.